📊 FigTabMiner Extraction Results

📄 2110.14774v1 (1).pdf

3
Total Items
2
Figures
1
Tables
0
Merged Items
FIGURE fig_0001
Score: 0.00
📄 Page 4 | 🔍 Source: unknown
fig_0001
Caption: Figure 3. SEM Images of the synthesised Iron oxide nanoparticles with reaction times A) 12 hrs, and B) 24hrs at 170°C.
FIGURE fig_0002
Score: 0.00
📄 Page 4 | 🔍 Source: unknown
fig_0002
Caption: Figure 3. SEM Images of the synthesised Iron oxide nanoparticles with reaction times A) 12 hrs, and B) 24hrs at 170°C.
TABLE table_0001
Score: 0.00
📄 Page 4 | 🔍 Source: unknown
table_0001
Caption: Fig.3).

📄 2112.02169v2.pdf

17
Total Items
9
Figures
8
Tables
0
Merged Items
FIGURE fig_0001
Score: 0.00
📄 Page 5 | 🔍 Source: unknown
fig_0001
Caption: Figure (1) Schematics of the ten aromatic molecules used in this study.
FIGURE fig_0002
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0002
Caption: Figure (2) Testing performance for the 10-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the first state.
FIGURE fig_0003
Score: 0.00
📄 Page 13 | 🔍 Source: unknown
fig_0003
Caption: Figure (3) Testing performance for the 7-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the first state. Molecules used in model generalization are indicated with blue panels.
FIGURE fig_0004
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0004
Caption: Figure (4) UV-Visible absorption spectra for all 10 aromatic molecules. Thick lines repre- sent the ML spectra predicted using the 10-molecule model and computed with the ensemble method. Thin lines represent the experimental reference.6,72–76 Dashed lines represent the calculated spectra using the multiscale quantum chemical method.
FIGURE fig_0005
Score: 0.00
📄 Page 16 | 🔍 Source: unknown
fig_0005
Caption: Figure (5) UV-Visible absorption spectra for all 10 aromatic molecules. Thick lines rep- resent the ML spectra computed with the ensemble method (dashed) and with the third order cumulant scheme (solid).21 Thin lines represent the experimental references.6,72–76 The spectra of the molecules not included in training set are highlighted with blue graph frames and labels.
FIGURE fig_0006
Score: 0.00
📄 Page 20 | 🔍 Source: unknown
fig_0006
Caption: Figure (6) Linear decomposition analysis from the 7-molecule model. %group are computed by averaging the excitation energy predictions of 5000 frames.
FIGURE fig_0007
Score: 0.00
📄 Page 21 | 🔍 Source: unknown
fig_0007
Caption: Figure (7) Testing performance for the 10-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the second state.
FIGURE fig_0008
Score: 0.00
📄 Page 21 | 🔍 Source: unknown
fig_0008
Caption: Figure (8) UV-Visible absorption spectra for all 10 aromatic molecules, including the first two excited states. Thick lines correspond to the ML spectra predicted using the 10-molecule model. Dotted lines represent the calculated spectra using the multiscale quantum chemical method.
FIGURE fig_0009
Score: 0.00
📄 Page 36 | 🔍 Source: unknown
fig_0009
Caption: No caption found.
TABLE table_0001
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
table_0001
Caption: Figure (2) Testing performance for the 10-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the first state.
TABLE table_0002
Score: 0.00
📄 Page 13 | 🔍 Source: unknown
table_0002
Caption: Figure (3) Testing performance for the 7-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the first state. Molecules used in model generalization are indicated with blue panels.
TABLE table_0003
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
table_0003
Caption: Figure (4) UV-Visible absorption spectra for all 10 aromatic molecules. Thick lines repre- sent the ML spectra predicted using the 10-molecule model and computed with the ensemble method. Thin lines represent the experimental reference.6,72–76 Dashed lines represent the calculated spectra using the multiscale quantum chemical method.
TABLE table_0004
Score: 0.00
📄 Page 16 | 🔍 Source: unknown
table_0004
Caption: Figure (5) UV-Visible absorption spectra for all 10 aromatic molecules. Thick lines rep- resent the ML spectra computed with the ensemble method (dashed) and with the third order cumulant scheme (solid).21 Thin lines represent the experimental references.6,72–76 The spectra of the molecules not included in training set are highlighted with blue graph frames and labels.
TABLE table_0005
Score: 0.00
📄 Page 20 | 🔍 Source: unknown
table_0005
Caption: Figure (6) Linear decomposition analysis from the 7-molecule model. %group are computed by averaging the excitation energy predictions of 5000 frames.
TABLE table_0006
Score: 0.00
📄 Page 21 | 🔍 Source: unknown
table_0006
Caption: Figure (7) Testing performance for the 10-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the second state.
TABLE table_0007
Score: 0.00
📄 Page 21 | 🔍 Source: unknown
table_0007
Caption: Figure (7) Testing performance for the 10-molecule model. εML is computed by averaging ε predictions from the 10-fold cross-validation. εQC is the quantum mechanically computed excitation energies for the second state.
TABLE table_0008
Score: 0.00
📄 Page 36 | 🔍 Source: unknown
table_0008
Caption: No caption found.

📄 2310.16875.pdf

6
Total Items
3
Figures
3
Tables
0
Merged Items
FIGURE fig_0001
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
fig_0001
Caption: FIG. 2. Density plot showing the distance upper limit for GW detectors (dUL GW) (see Eq. 5) for CE (left), ET (middle), and ET+CE (right) on the δt - fth plane.
FIGURE fig_0002
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
fig_0002
Caption: FIG. 2. Density plot showing the distance upper limit for GW detectors (dUL GW) (see Eq. 5) for CE (left), ET (middle), and ET+CE (right) on the δt - fth plane.
FIGURE fig_0003
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
fig_0003
Caption: FIG. 2. Density plot showing the distance upper limit for GW detectors (dUL GW) (see Eq. 5) for CE (left), ET (middle), and ET+CE (right) on the δt - fth plane.
TABLE table_0001
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
table_0001
Caption: FIG. 2. Density plot showing the distance upper limit for GW detectors (dUL GW) (see Eq. 5) for CE (left), ET (middle), and ET+CE (right) on the δt - fth plane.
TABLE table_0002
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
table_0002
Caption: FIG. 2. Density plot showing the distance upper limit for GW detectors (dUL GW) (see Eq. 5) for CE (left), ET (middle), and ET+CE (right) on the δt - fth plane.
TABLE table_0003
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
table_0003
Caption: FIG. 2. Density plot showing the distance upper limit for GW detectors (dUL GW) (see Eq. 5) for CE (left), ET (middle), and ET+CE (right) on the δt - fth plane.

📄 2304.12999v1.pdf

34
Total Items
29
Figures
5
Tables
0
Merged Items
FIGURE fig_0001
Score: 0.00
📄 Page 10 | 🔍 Source: unknown
fig_0001
Caption: Figure 4 Schematics drawings of emitted electrons contributing to different contrasts. (a) Energy distribution of
FIGURE fig_0002
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0002
Caption: No matching caption found.
FIGURE fig_0003
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0003
Caption: No matching caption found.
FIGURE fig_0004
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0004
Caption: No matching caption found.
FIGURE fig_0005
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0005
Caption: Figure 5 Contrast separation by changing the WD. (a) Sketch drawing of the
FIGURE fig_0006
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0006
Caption: Figure 5 Contrast separation by changing the WD. (a) Sketch drawing of the
FIGURE fig_0007
Score: 0.00
📄 Page 12 | 🔍 Source: unknown
fig_0007
Caption: Figure 5 Contrast separation by changing the WD. (a) Sketch drawing of the
FIGURE fig_0008
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0008
Caption: Figure 6 Contrast separation by changing the deceleration voltage in the Hitachi
FIGURE fig_0009
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0009
Caption: Figure 6 Contrast separation by changing the deceleration voltage in the Hitachi
FIGURE fig_0010
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0010
Caption: Figure 6 Contrast separation by changing the deceleration voltage in the Hitachi
FIGURE fig_0011
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0011
Caption: Figure 6 Contrast separation by changing the deceleration voltage in the Hitachi
FIGURE fig_0012
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0012
Caption: Figure 6 Contrast separation by changing the deceleration voltage in the Hitachi
FIGURE fig_0013
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0013
Caption: Figure 6 Contrast separation by changing the deceleration voltage in the Hitachi
FIGURE fig_0014
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0014
Caption: No matching caption found.
FIGURE fig_0015
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
fig_0015
Caption: No matching caption found.
FIGURE fig_0016
Score: 0.00
📄 Page 17 | 🔍 Source: unknown
fig_0016
Caption: Figure 7 Contrast evolution due to the electron-beam-induced deposition in LVSEM images of polymer-sorted
FIGURE fig_0017
Score: 0.00
📄 Page 19 | 🔍 Source: unknown
fig_0017
Caption: Figure 8 LVSEM contrast separation of a CVD-grown CNT using a Hitachi Regulus
FIGURE fig_0018
Score: 0.00
📄 Page 20 | 🔍 Source: unknown
fig_0018
Caption: Figure 9 LVSEM and cross-section STEM images of a polymer-sorted CNT array. (a) LVSEM image obtained
FIGURE fig_0019
Score: 0.00
📄 Page 20 | 🔍 Source: unknown
fig_0019
Caption: Figure 9 LVSEM and cross-section STEM images of a polymer-sorted CNT array. (a) LVSEM image obtained
FIGURE fig_0020
Score: 0.00
📄 Page 20 | 🔍 Source: unknown
fig_0020
Caption: Figure 9 LVSEM and cross-section STEM images of a polymer-sorted CNT array. (a) LVSEM image obtained
FIGURE fig_0021
Score: 0.00
📄 Page 28 | 🔍 Source: unknown
fig_0021
Caption: Figure S3 The acceptance map of the Inlens detector at a WD of (a) 1 mm, (b) 3 mm, and (c) 5 mm.
FIGURE fig_0022
Score: 0.00
📄 Page 28 | 🔍 Source: unknown
fig_0022
Caption: Figure S3 The acceptance map of the Inlens detector at a WD of (a) 1 mm, (b) 3 mm, and (c) 5 mm.
FIGURE fig_0023
Score: 0.00
📄 Page 28 | 🔍 Source: unknown
fig_0023
Caption: Figure S4 SEM images of an uncleaned polymer-sorted CNT array. (a) Before and (b) after annealing in Ar gas at 350 ℃ for 1 hour. A WD of 5 mm is used to emphasize the material difference. The yellow arrow indicates the contrast referece, i.e. bright contrast of the bare substrate near the edge of the CNT arrays. White spots circled in red indicate the partial removal of the covered polymers. (c) θ
FIGURE fig_0024
Score: 0.00
📄 Page 28 | 🔍 Source: unknown
fig_0024
Caption: Figure S4 SEM images of an uncleaned polymer-sorted CNT array. (a) Before and (b) after annealing in Ar gas at 350 ℃ for 1 hour. A WD of 5 mm is used to emphasize the material difference. The yellow arrow indicates the contrast referece, i.e. bright contrast of the bare substrate near the edge of the CNT arrays. White spots circled in red indicate the partial removal of the covered polymers. (c) θ
FIGURE fig_0025
Score: 0.00
📄 Page 29 | 🔍 Source: unknown
fig_0025
Caption: Figure S5 The acceptance map of the Upper and Top detectors at a Vdec of (a) 0, (b) -100 V, and (c) -
FIGURE fig_0026
Score: 0.00
📄 Page 29 | 🔍 Source: unknown
fig_0026
Caption: Figure S5 The acceptance map of the Upper and Top detectors at a Vdec of (a) 0, (b) -100 V, and (c) -
FIGURE fig_0027
Score: 0.00
📄 Page 29 | 🔍 Source: unknown
fig_0027
Caption: Figure S5 The acceptance map of the Upper and Top detectors at a Vdec of (a) 0, (b) -100 V, and (c) -
FIGURE fig_0028
Score: 0.00
📄 Page 29 | 🔍 Source: unknown
fig_0028
Caption: Figure S6 Statistics of the number of CNTs in 1 μm in the typical region. (a) A LVSEM image
FIGURE fig_0029
Score: 0.00
📄 Page 30 | 🔍 Source: unknown
fig_0029
Caption: Table 1 Imaging parameters of the two SEM instruments. The beam current is measured by a Faraday
TABLE table_0001
Score: 0.00
📄 Page 8 | 🔍 Source: unknown
table_0001
Caption: Figure 2 Schematics illustrating the charge contrast of a single CNT, a low-density CNT array (pitch> 30 nm),
TABLE table_0002
Score: 0.00
📄 Page 8 | 🔍 Source: unknown
table_0002
Caption: Figure 2 Schematics illustrating the charge contrast of a single CNT, a low-density CNT array (pitch> 30 nm),
TABLE table_0003
Score: 0.00
📄 Page 8 | 🔍 Source: unknown
table_0003
Caption: Figure 2 Schematics illustrating the charge contrast of a single CNT, a low-density CNT array (pitch> 30 nm),
TABLE table_0004
Score: 0.00
📄 Page 10 | 🔍 Source: unknown
table_0004
Caption: Figure 4 Schematics drawings of emitted electrons contributing to different contrasts. (a) Energy distribution of
TABLE table_0005
Score: 0.00
📄 Page 17 | 🔍 Source: unknown
table_0005
Caption: Figure 7 Contrast evolution due to the electron-beam-induced deposition in LVSEM images of polymer-sorted

📄 2508.08441v1.pdf

4
Total Items
3
Figures
1
Tables
0
Merged Items
FIGURE fig_0001
Score: 0.00
📄 Page 4 | 🔍 Source: unknown
fig_0001
Caption: Fig. 1: Overview of the training pipeline for structure elucidation. Characteristic spectral peaks are extracted from raw IR, Raman, UV, NMR, or MS data and used to construct natural language prompts. These are input to a frozen large language model fine-tuned via LoRA. The model is trained to autoregressively generate molecular structures in SMILES format, supervised by the ground-truth sequence.
FIGURE fig_0002
Score: 0.00
📄 Page 6 | 🔍 Source: unknown
fig_0002
Caption: Fig. 2: Effect of Raman spectra on structural prediction accuracy. Three representative examples where incorporating Raman spectra corrects wrong predictions made using only IR or UV-Vis inputs. This highlights Raman’s complementary role in resolving molecular substructures sensitive to polarizability.
FIGURE fig_0003
Score: 0.00
📄 Page 7 | 🔍 Source: unknown
fig_0003
Caption: Fig. 3: Importance of IR spectra for identifying functional groups. Three representa- tive examples where IR spectra are essential to correctly identify carbonyl groups and distinguish branched chain configurations. Without IR input, predictions based on Raman and UV-Vis remain ambiguous or incorrect.
TABLE table_0001
Score: 0.00
📄 Page 15 | 🔍 Source: unknown
table_0001
Caption: Table 6: Data distribution across spectral modalities and splits.

📈 Overall Summary

5
Documents Processed
46
Total Figures
18
Total Tables
0
Merged Items